Update app.py

app.py

@@ -234,33 +234,70 @@ class AttendanceSystem:
 
     # --- Video Processing ---
     def process_frame(self, frame: np.ndarray) -> np.ndarray:
+        """
+        Main function to process a single video frame with added debugging prints.
+        """
         try:
             face_objs = DeepFace.extract_faces(img_path=frame, detector_backend='opencv', enforce_detection=False)
-            for face_obj in face_objs:
-                if face_obj['confidence'] < 0.95: continue
+
+            # Print a summary for the current frame
+            if face_objs:
+                print(f"\n--- Frame Processed: Found {len(face_objs)} faces. ---")
+
+            for i, face_obj in enumerate(face_objs):
+                confidence = face_obj['confidence']
+                print(f"  Face #{i+1}: Confidence Score = {confidence:.2f}")
+
+                if confidence < 0.95:
+                    print("    -> Confidence too low, skipping.")
+                    continue
+
                 x, y, w, h = face_obj['facial_area'].values()
                 face_image = frame[y:y+h, x:x+w]
+                
                 if face_image.size == 0: continue
+
                 embedding = DeepFace.represent(img_path=face_image, model_name='Facenet', enforce_detection=False)[0]['embedding']
-                distances = [np.linalg.norm(np.array(embedding) - known) for known in self.known_face_embeddings] if self.known_face_embeddings else []
-                min_dist = min(distances) if distances else float('inf')
+                
+                if not self.known_face_embeddings:
+                    print("    -> No known faces in database to compare against.")
+                    continue
+
+                distances = [np.linalg.norm(np.array(embedding) - known) for known in self.known_face_embeddings]
+                min_dist = min(distances)
                 match_index = distances.index(min_dist) if min_dist < 10.0 else -1
+
+                print(f"    -> Comparing to DB... Minimum Distance Found: {min_dist:.4f}")
+
                 color, worker_id, worker_name = (0, 0, 255), None, "Unknown"
+                
                 if match_index != -1:
-                    worker_id, worker_name, color = self.known_face_ids[match_index], self.known_face_names[match_index], (0, 255, 0)
-                    if self.mark_attendance(worker_id, worker_name): self.last_recognition_time[worker_id] = time.time()
+                    worker_id = self.known_face_ids[match_index]
+                    worker_name = self.known_face_names[match_index]
+                    color = (0, 255, 0) # Green
+                    print(f"    ✓ MATCH! (Threshold: 10.0). Recognized as {worker_name}")
+                    if self.mark_attendance(worker_id, worker_name):
+                        self.last_recognition_time[worker_id] = time.time()
                 else:
+                    color = (0, 165, 255) # Orange for potential new worker
+                    print(f"    ✗ NO MATCH (Threshold: 10.0). Registering as new worker...")
                     new_worker = self._register_worker_auto(face_image)
                     if new_worker:
-                        worker_id, worker_name, color = new_worker[0], new_worker[1], (0, 165, 255)
-                        if self.mark_attendance(worker_id, worker_name): self.last_recognition_time[worker_id] = time.time()
+                        worker_id, worker_name = new_worker[0], new_worker[1]
+                        if self.mark_attendance(worker_id, worker_name):
+                            self.last_recognition_time[worker_id] = time.time()
+                
                 label = f"{worker_name}" + (f" ({worker_id})" if worker_id else "")
                 cv2.rectangle(frame, (x, y), (x+w, y+h), color, 2)
                 cv2.putText(frame, label, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 0.7, color, 2)
+
             return frame
-        except Exception:
+        except Exception as e:
+            # This will catch errors during the representation/matching phase
+            print(f"ERROR in process_frame: {e}")
             return frame
 
+
     def _processing_loop(self, source):
         video_capture = cv2.VideoCapture(source)
         if not video_capture.isOpened():